Filter saved reasoning overrides from requests when disabled (#46291)

## Why

Resuming a thread after disabling reasoning effort overrides still sent saved `configuration_update` items until compaction. Disabling the feature should also apply to requests built from existing history.

## What changed

Pass the `ReasoningEffortOverride` feature state into `ModelClient` and filter `configuration_update` items from request input when disabled. Preserve persisted history and other input items while using the request-level reasoning effort.

## Testing

Add regression coverage for resumed threads, compaction, and WebSocket warmup and turn requests. Verify that saved updates remain in history and `agent_message` items remain in request input.

GitOrigin-RevId: aac3257da1ca38a0744807c4f7cb12565bd7fe53

codex-rs/core/src/client.rs

@@ -203,6 +203,7 @@ struct ModelClientState {
     originator: String,
     model_verbosity: Option<VerbosityConfig>,
     content_item_kinds_enabled: bool,
+    reasoning_effort_override_enabled: bool,
     enable_request_compression: bool,
     include_timing_metrics: bool,
     beta_features_header: Option<String>,
@@ -476,6 +477,7 @@ impl ModelClient {
         originator: String,
         model_verbosity: Option<VerbosityConfig>,
         content_item_kinds_enabled: bool,
+        reasoning_effort_override_enabled: bool,
         enable_request_compression: bool,
         include_timing_metrics: bool,
         beta_features_header: Option<String>,
@@ -502,6 +504,7 @@ impl ModelClient {
                 originator,
                 model_verbosity,
                 content_item_kinds_enabled,
+                reasoning_effort_override_enabled,
                 enable_request_compression,
                 include_timing_metrics,
                 beta_features_header,
@@ -856,6 +859,11 @@ impl ModelClient {
         responses_metadata: &CodexResponsesMetadata,
     ) -> Result<ResponsesApiRequest> {
         let mut input = prompt.get_formatted_input_for_request(model_info);
+        if !self.state.reasoning_effort_override_enabled {
+            // Disabling overrides must also recover threads with saved updates.
+            // Filter only the request copy; persisted history remains unchanged.
+            input.retain(|item| !matches!(item, ResponseItem::ConfigurationUpdate { .. }));
+        }
         let is_openai = self.state.provider.info().is_openai();
         let (instructions, tools) = if model_info.use_responses_lite {
             // These prompt-only items are rebuilt on every request. Hash their visible payloads

codex-rs/core/src/client_tests.rs

@@ -115,6 +115,7 @@ fn test_model_client_with_thread_id(
         "test_originator".to_string(),
         /*model_verbosity*/ None,
         /*content_item_kinds_enabled*/ true,
+        /*reasoning_effort_override_enabled*/ false,
         /*enable_request_compression*/ false,
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,
@@ -1631,6 +1632,7 @@ fn model_client_with_counting_attestation(
         "test_originator".to_string(),
         /*model_verbosity*/ None,
         /*content_item_kinds_enabled*/ true,
+        /*reasoning_effort_override_enabled*/ false,
         /*enable_request_compression*/ false,
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,

codex-rs/core/src/session/session.rs

@@ -1677,6 +1677,7 @@ impl Session {
                     session_configuration.originator.clone(),
                     config.model_verbosity,
                     config.features.enabled(Feature::ContentItemKinds),
+                    config.features.enabled(Feature::ReasoningEffortOverride),
                     config.features.enabled(Feature::EnableRequestCompression),
                     config.features.enabled(Feature::RuntimeMetrics),
                     Self::build_model_client_beta_features_header(config.as_ref()),

codex-rs/core/src/session/tests.rs

@@ -794,6 +794,7 @@ fn test_model_client_session() -> crate::client::ModelClientSession {
         "test_originator".to_string(),
         /*model_verbosity*/ None,
         /*content_item_kinds_enabled*/ true,
+        /*reasoning_effort_override_enabled*/ false,
         /*enable_request_compression*/ false,
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,
@@ -6177,6 +6178,7 @@ pub(crate) async fn make_session_and_context() -> (Session, TurnContext) {
             session_configuration.originator.clone(),
             config.model_verbosity,
             config.features.enabled(Feature::ContentItemKinds),
+            config.features.enabled(Feature::ReasoningEffortOverride),
             config.features.enabled(Feature::EnableRequestCompression),
             config.features.enabled(Feature::RuntimeMetrics),
             Session::build_model_client_beta_features_header(config.as_ref()),
@@ -8363,6 +8365,7 @@ where
             session_configuration.originator.clone(),
             config.model_verbosity,
             config.features.enabled(Feature::ContentItemKinds),
+            config.features.enabled(Feature::ReasoningEffortOverride),
             config.features.enabled(Feature::EnableRequestCompression),
             config.features.enabled(Feature::RuntimeMetrics),
             Session::build_model_client_beta_features_header(config.as_ref()),